Identifying potential problems in a pumpjack

Abstract

Methods, computer program products, and/or systems are provided that perform the following operations: obtaining a series of indicator diagrams corresponding to strokes of a pumpjack over a specific time duration, dividing each indicator diagram into a plurality of location segments in a direction of location of the rod; obtaining load difference features between upstroke loads and corresponding downstroke loads in the plurality of location segments; identifying a location segment with an abnormal load difference feature based on a time series data of load difference feature corresponding to one of the plurality of location segments, the time series data of load difference feature including a series of data points of load difference feature of the one of the plurality of location segments in time order; and providing an indication of a potential problem based, at least in part, on the identification of the location segment with an abnormal load difference feature.

What is claimed is: 
     
       1. A computer-implemented method comprising:
 obtaining a series of indicator diagrams corresponding to strokes of a pumpjack over a specific time duration, each indicator diagram representing a relationship between location and load of a rod of the pumpjack throughout a stroke of the pumpjack; 
 for each indicator diagram of the series of indicator diagrams:
 dividing each indicator diagram into a plurality of location segments in a direction of the location of the rod, and 
 obtaining load difference features between upstroke loads and corresponding downstroke loads in the plurality of location segments; 
 
 identifying a location segment with an abnormal load difference feature based on a time series data of load difference feature corresponding to one of the plurality of location segments, wherein the time series data of load difference feature includes a series of data points of load difference feature of the one of the plurality of location segments in time order; and 
 providing an indication of a potential pumpjack problem based, at least in part, on identification of the location segment with the abnormal load difference feature. 
 
     
     
       2. The computer-implemented method of  claim 1 , further comprising:
 identifying a trend measure of the potential pumpjack problem corresponding to the identified location segment based on the time series data of load difference feature, wherein the trend measure indicates a change degree of the load difference features during the specific time duration. 
 
     
     
       3. The computer-implemented method of  claim 2 , further comprising:
 classifying identified location segments based on a variation of load difference feature in the time series data of load difference feature and trend measures of the identified location segments. 
 
     
     
       4. The computer-implemented method of  claim 2 , wherein identifying the trend measure of the potential pumpjack problem corresponding to the identified location segment based on the time series data of load difference feature comprises:
 fitting the time series data of load difference feature for the location segment using an exponential smoothing model; and 
 providing a smoothing factor of the exponential smoothing model as the trend measure. 
 
     
     
       5. The computer-implemented method of  claim 1 , wherein identifying the location segment with the abnormal load difference feature based on the time series data of load difference feature corresponding to one of the plurality of location segments comprises:
 obtaining a variation of load difference feature in the time series data of load difference feature corresponding to one of the plurality of location segments; and 
 identifying the location segment with the abnormal load difference feature in response to the variation of load difference of a specific location segment exceeding a threshold. 
 
     
     
       6. The computer-implemented method of  claim 5 , wherein obtaining the variation of load difference feature in the time series data of load difference feature comprises:
 obtaining the load difference features within a specified time window in the time series data of load difference feature; and 
 determining the variation of load difference feature based on the load difference features within the specified time window. 
 
     
     
       7. The computer-implemented method of  claim 6 , wherein the variation of load difference feature is a difference between a maximum load difference feature and a minimum load difference feature within the specified time window. 
     
     
       8. A computer system comprising:
 one or more processing units; and 
 a memory coupled to the one or more processing units and storing instructions thereon, the instructions, when executed by the one or more processing units, performing operations comprising:
 obtaining a series of indicator diagrams corresponding to strokes of a pumpjack over a specific time duration, each indicator diagram representing a relationship between location and load of a rod of the pumpjack throughout a stroke of the pumpjack; 
 for each indicator diagram of the series of indicator diagrams:
 dividing each indicator diagram into a plurality of location segments in a direction of the location of the rod, and 
 obtaining load difference features between upstroke loads and corresponding downstroke loads in the plurality of location segments; 
 
 identifying a location segment with an abnormal load difference feature based on a time series data of load difference feature corresponding to one of the plurality of location segments, wherein the time series data of load difference feature includes a series of data points of load difference feature of the one of the plurality of location segments in time order; and 
 providing an indication of a potential pumpjack problem based, at least in part, on the identification of the location segment with the abnormal load difference feature. 
 
 
     
     
       9. The computer system of  claim 8 , the operations further comprising:
 identifying a trend measure of the potential pumpjack problem corresponding to the identified location segment based on the time series data of load difference feature, wherein the trend measure indicates a change degree of the load difference features during the specific time duration. 
 
     
     
       10. The computer system of  claim 9 , the operations further comprising:
 classifying identified location segments based on a variation of load difference feature in the time series data of load difference feature and trend measures of the identified location segments. 
 
     
     
       11. The computer system of  claim 9 , wherein identifying the trend measure of the potential pumpjack problem corresponding to the identified location segment based on the time series data of load difference feature comprises:
 fitting the time series data of load difference feature for the location segment using an exponential smoothing model; and 
 providing a smoothing factor of the exponential smoothing model as the trend measure. 
 
     
     
       12. The computer system of  claim 8 , wherein identifying the location segment with the abnormal load difference feature based on the time series data of load difference feature corresponding to one of the plurality of location segments comprises:
 obtaining a variation of load difference feature in the time series data of load difference feature corresponding to one of the plurality of location segments; and 
 identifying the location segment with the abnormal load difference feature in response to the variation of load difference of a specific location segment exceeding a threshold. 
 
     
     
       13. The computer system of  claim 12 , wherein obtaining the variation of load difference feature in the time series data of load difference feature comprises:
 obtaining the load difference features within a specified time window in the time series data of load difference feature; and 
 determining the variation of load difference feature based on the load difference features within the specified time window. 
 
     
     
       14. The computer system of  claim 13 , wherein the variation of load difference feature is a difference between a maximum load difference feature and a minimum load difference feature within the specified time window. 
     
     
       15. A computer program product comprising a non-transitory computer readable storage medium having stored thereon:
 program instructions programmed to obtain a series of indicator diagrams corresponding to strokes of a pumpjack over a specific time duration, each indicator diagram representing a relationship between location and load of a rod of the pumpjack throughout a stroke of the pumpjack; 
 for each indicator diagram of the series of indicator diagrams:
 program instructions programmed to divide each indicator diagram into a plurality of location segments in a direction of the location of the rod, and 
 program instructions programmed to obtain load difference features between upstroke loads and corresponding downstroke loads in the plurality of location segments; 
 
 program instructions programmed to identify a location segment with an abnormal load difference feature based on a time series data of load difference feature corresponding to one of the plurality of location segments, wherein the time series data of load difference feature includes a series of data points of load difference feature of the one of the plurality of location segments in time order; and 
 program instructions programmed to provide an indication of a potential pumpjack problem based, at least in part, on the identification of the location segment with the abnormal load difference feature. 
 
     
     
       16. The computer program product of  claim 15 , the non-transitory computer readable storage medium having further stored thereon:
 program instructions programmed to identify a trend measure of the potential pumpjack problem corresponding to the identified location segment based on the time series data of load difference feature, wherein the trend measure indicates a change degree of the load difference features during the specific time duration. 
 
     
     
       17. The computer program product of  claim 16 , the non-transitory computer readable storage medium having further stored thereon:
 program instructions programmed to classify the identified location segments based on a variation of load difference feature in the time series data of load difference feature and trend measures of the identified location segments. 
 
     
     
       18. The computer program product of  claim 16 , wherein the program instructions programmed to identify the trend measure of the potential pumpjack problem corresponding to the identified location segment based on the time series data of load difference feature comprises:
 program instructions programmed to fit the time series data of load difference feature for the location segment using an exponential smoothing model; and 
 program instructions programmed to provide a smoothing factor of the exponential smoothing model as the trend measure. 
 
     
     
       19. The computer program product of  claim 15 , wherein the program instructions programmed to identifying the location segment with the abnormal load difference feature based on the time series data of load difference feature corresponding to one of the plurality of location segments comprise:
 program instructions programmed to obtain a variation of load difference feature in the time series data of load difference feature corresponding to one of the plurality of location segments; and 
 program instructions programmed to identify the location segment with the abnormal load difference feature in response to the variation of load difference of a specific location segment exceeding a threshold. 
 
     
     
       20. The computer program product of  claim 19 , wherein the program instructions programmed to obtain the variation of load difference feature in the time series data of load difference feature comprises:
 program instructions programmed to obtain the load difference features within a specified time window in the time series data of load difference feature; and 
 program instructions programmed to determine the variation of load difference feature based on the load difference features within the specified time window.